nanoGRPO is a lightweight implementation of Group Relative Policy Optimization (GRPO)
☆143May 8, 2025Updated last year
Alternatives and similar repositories for nanoGRPO
Users that are interested in nanoGRPO are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Official Pytorch Implementation of "Zero-Shot Off-Policy Learning" (ICML 2026)☆25Feb 16, 2026Updated 5 months ago
- ☆45Mar 31, 2025Updated last year
- streaming deep reinforcement learning but 4x faster with jax!☆19Jan 4, 2026Updated 6 months ago
- Official Implementation of `An Optimisation Framework for Unsupervised Environment Design` from RLC 2025☆17Nov 24, 2025Updated 7 months ago
- NanoGPT-speedrunning for the poor T4 enjoyers☆72Apr 22, 2025Updated last year
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- ☆10Oct 11, 2022Updated 3 years ago
- Opinionated library for managing hyperparameters and mutable state of machine learning training systems.☆19Aug 4, 2023Updated 2 years ago
- RLHF experiments on a single A100 40G GPU. Support PPO, GRPO, REINFORCE, RAFT, RLOO, ReMax, DeepSeek R1-Zero reproducing.☆80Feb 19, 2025Updated last year
- Real-Time RTUs☆12Mar 20, 2026Updated 4 months ago
- Fast reinforcement learning 💨☆29Jul 15, 2025Updated last year
- OpenAI gym environments for goal-conditioned and language-conditioned reinforcement learning☆14Jan 27, 2026Updated 5 months ago
- This repo contains a demo of adversarial strings poisoning vector database and forching specific hallucinations on RAG chatbot.☆10May 2, 2024Updated 2 years ago
- Actor-Sharer-Learner training framework for off-policy DRL algorithms☆22Dec 29, 2024Updated last year
- This is a repo covers ai research papers pseudocodes☆18Jun 20, 2023Updated 3 years ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Understanding R1-Zero-Like Training: A Critical Perspective☆1,267Aug 27, 2025Updated 10 months ago
- Minimal hackable GRPO implementation☆344Jan 31, 2025Updated last year
- [ICML 2023] Code for paper "Internally Rewarded Reinforcement Learning"☆13Jul 21, 2023Updated 3 years ago
- Agar.io for Continual Reinforcement Learning☆24Jul 24, 2025Updated 11 months ago
- A basic pure pytorch implementation of flash attention☆17Oct 28, 2024Updated last year
- Code for "LifeLong Incremental Reinforcement Learning (LLIRL)"☆21Jan 28, 2021Updated 5 years ago
- Official PyTorch Implementation of the Longhorn Deep State Space Model☆57Dec 4, 2024Updated last year
- rl from zero pretrain, can it be done? yes.☆295Sep 28, 2025Updated 9 months ago
- A bespoke time‑first language + toolchain for hybrid Neuromorphic - classical systems☆11Feb 4, 2026Updated 5 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Monte Carlo Tree Search Self-Refine (MCTSr)☆21Jul 6, 2024Updated 2 years ago
- Muon is Scalable for LLM Training☆1,508Aug 3, 2025Updated 11 months ago
- ☆21Dec 22, 2020Updated 5 years ago
- Official implementation of the RLC 2024 paper "Policy-Guided Diffusion"☆153Jul 19, 2024Updated 2 years ago
- Official implementation for the LABOR (LAnguage-model-based Bimanual ORchestration) Agent.☆23Nov 23, 2024Updated last year
- Object-Centric-Representation Library (OCRL): This repo is to explore OCR on various downstream tasks from supervised learning tasks to R…☆12Feb 23, 2024Updated 2 years ago
- ☆10Jun 27, 2024Updated 2 years ago
- Experiments Notebook of "Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism"☆16Apr 30, 2025Updated last year
- ☆12Sep 7, 2024Updated last year
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- VC-FB and MC-FB algorithms from "Zero-Shot Reinforcement Learning from Low Quality Data" (NeurIPS 2024)☆29Jan 14, 2025Updated last year
- GCRL in JAX. Official repository for LEO (ICML 2026).☆27Jun 20, 2026Updated last month
- Official implementation of Zero-Hero paper☆31Feb 13, 2025Updated last year
- ☆19Jul 4, 2025Updated last year
- ☆10Dec 10, 2024Updated last year
- Single File, Single GPU, From Scratch, Efficient, Full Parameter Tuning library for "RL for LLMs"☆625Oct 7, 2025Updated 9 months ago
- Simple single-file baselines for Q-Learning in pure-GPU setting☆242Nov 24, 2025Updated 7 months ago